Parse AIS (Annual Information Statement)

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds real context beyond the annotations: processing is on-device (consistent with openWorldHint=false), the decryption scheme is reverse-engineered and may fail, and the return payload is described. Missing are error semantics for a wrong password or malformed JSON, which matter for a tool whose own description admits fragility.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four tight sentences, front-loaded with the action and privacy property, then credentials, then return shape, then fallback. The fallback/issue sentence is slightly operational-tangent but still earns its place as recovery guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly carries the return-shape burden ('taxpayer info and normalized information rows... with amounts, dates, and codes'). Combined with the fragility disclosure, an agent has enough to call it and to interpret partial failures, though failure-mode behavior remains unspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already documents the overrides relationship for password. The description restates the pan+dob derivation hint but adds no format or edge-case detail (e.g., non-individual DOB handling, PAN case sensitivity) beyond what the schema provides. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb pair and resource ('Decrypt and parse the AIS JSON export from the income tax portal') plus scope ('entirely on-device'). The document-specific framing (AIS JSON, not Form 26AS) lets an agent distinguish it from the sibling parse_form26as without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explains the two credential paths ('provide pan + dob to derive the password, or pass it explicitly') and gives an explicit failure path (fall back to the portal's CSV export, file an issue). It does not explicitly route between this and parse_form26as when a user has both documents, which keeps it below a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.